Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Information System, Applied, Management, Accounting and Research
M Sabir, Fitriana
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
SISTEM PERINGATAN DINI BANJIR BERBASIS SUPPORT VECTOR MACHINE YANG DIOPTIMALKAN DENGAN PARTICLE SWARM OPTIMIZATION Rizal H, Muhammad; M Sabir, Fitriana; Mursalim, Mursalim
Journal of Information System, Applied, Management, Accounting and Research Vol 10 No 1 (2026): JISAMAR (February 2026)
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52362/jisamar.v10i1.2260

Abstract

Flooding is one of the most frequently occurring hydrometeorological disasters and causes substantial impacts on human safety, infrastructure damage, and economic losses. This condition necessitates the development of flood early warning systems that are accurate, reliable, and capable of providing timely information. This study aims to develop a flood early warning system based on Support Vector Machine optimized using Particle Swarm Optimization to improve the prediction performance of flood events. The methodology involves constructing a Support Vector Machine model with hyperparameter optimization carried out through Particle Swarm Optimization. The performance of the proposed model is compared with a Support Vector Machine without optimization and a Support Vector Machine optimized using the GridSearch method. Model performance is evaluated using several metrics, including accuracy, precision, recall, F1-score, and specificity, and is further analyzed through confusion matrices, learning curves, Receiver Operating Characteristic curves, and optimization convergence. The results demonstrate that the Support Vector Machine–Particle Swarm Optimization model achieves the best performance, with an accuracy of approximately 96% and an optimal F1-score of 0.9777. The model successfully detects all flood events without any false negatives and produces only one false positive, indicating very high sensitivity and reliability. Learning curve analysis shows stable generalization capability, while the optimization process exhibits rapid and consistent convergence in the early iterations. Compared with the benchmark models, this approach also provides better classification balance and higher computational efficiency
Co-Authors Mursalim Mursalim Rizal H, Muhammad